← Search

Jiu Feng

2 accepted papers

2024

From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers

ICASSP 2024accepted

Transformers have become central to recent advances in audio classification. However, training an audio spectrogram transformer, e.g. AST, from scratch can be resource and time-intensive. Furthermore, the complexity of transformers heavily depends on the input audio spectrogram size. In this work, w…

Cited by 0SourceScholar
2022

Decoupled Adversarial Contrastive Learning for Self-Supervised Adversarial Robustness

ECCV 2022poster

"\textit{Adversarial training} (AT) for robust representation learning and \textit{self-supervised learning} (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a highly significant yet challenging task: learn…